user/sven/linux.git/kernel/rcu/refscale.c, branch v5.15.141

refscale: Fix uninitalized use of wait_queue_head_t

2023-09-19T10:22:31Z

[ Upstream commit f5063e8948dad7f31adb007284a5d5038ae31bb8 ] Running the refscale test occasionally crashes the kernel with the following error: [ 8569.952896] BUG: unable to handle page fault for address: ffffffffffffffe8 [ 8569.952900] #PF: supervisor read access in kernel mode [ 8569.952902] #PF: error_code(0x0000) - not-present page [ 8569.952904] PGD c4b048067 P4D c4b049067 PUD c4b04b067 PMD 0 [ 8569.952910] Oops: 0000 [#1] PREEMPT_RT SMP NOPTI [ 8569.952916] Hardware name: Dell Inc. PowerEdge R750/0WMWCR, BIOS 1.2.4 05/28/2021 [ 8569.952917] RIP: 0010:prepare_to_wait_event+0x101/0x190 : [ 8569.952940] Call Trace: [ 8569.952941] [ 8569.952944] ref_scale_reader+0x380/0x4a0 [refscale] [ 8569.952959] kthread+0x10e/0x130 [ 8569.952966] ret_from_fork+0x1f/0x30 [ 8569.952973] The likely cause is that init_waitqueue_head() is called after the call to the torture_create_kthread() function that creates the ref_scale_reader kthread. Although this init_waitqueue_head() call will very likely complete before this kthread is created and starts running, it is possible that the calling kthread will be delayed between the calls to torture_create_kthread() and init_waitqueue_head(). In this case, the new kthread will use the waitqueue head before it is properly initialized, which is not good for the kernel's health and well-being. The above crash happened here: static inline void __add_wait_queue(...) { : if (!(wq->flags & WQ_FLAG_PRIORITY)) <=== Crash here The offset of flags from list_head entry in wait_queue_entry is -0x18. If reader_tasks[i].wq.head.next is NULL as allocated reader_task structure is zero initialized, the instruction will try to access address 0xffffffffffffffe8, which is exactly the fault address listed above. This commit therefore invokes init_waitqueue_head() before creating the kthread. Fixes: 653ed64b01dc ("refperf: Add a test to measure performance of read-side synchronization") Signed-off-by: Waiman Long Reviewed-by: Qiuxu Zhuo Reviewed-by: Davidlohr Bueso Acked-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin

refscale: Move shutdown from wait_event() to wait_event_idle()

2023-05-24T16:36:43Z

[ Upstream commit 6bc6e6b27524304aadb9c04611ddb1c84dd7617a ] The ref_scale_shutdown() kthread/function uses wait_event() to wait for the refscale test to complete. However, although the read-side tests are normally extremely fast, there is no law against specifying a very large value for the refscale.loops module parameter or against having a slow read-side primitive. Either way, this might well trigger the hung-task timeout. This commit therefore replaces those wait_event() calls with calls to wait_event_idle(), which do not trigger the hung-task timeout. Signed-off-by: Paul E. McKenney Signed-off-by: Boqun Feng Signed-off-by: Sasha Levin

refscale: Add measurement of clock readout

2021-07-27T18:38:56Z

This commit adds a "clock" type to refscale, which checks the performance of ktime_get_real_fast_ns(). Use the "clocksource=" kernel boot parameter to select the underlying clock source. [ paulmck: Work around compiler false positive per kernel test robot. ] Signed-off-by: Paul E. McKenney

refscale: Avoid false-positive warnings in ref_scale_reader()

2021-07-06T19:38:08Z

If the call to set_cpus_allowed_ptr() in ref_scale_reader() fails, a later WARN_ONCE() complains. But with the advent of 570a752b7a9b ("lib/smp_processor_id: Use is_percpu_thread() instead of nr_cpus_allowed"), this complaint can be drowned out by complaints from smp_processor_id(). The rationale for this change is that refscale's kthreads are not marked with PF_NO_SETAFFINITY, which means that a system administrator could change affinity at any time. However, refscale is a performance/stress test, and the system administrator might well have a valid test-the-test reason for changing affinity. This commit therefore changes to raw_smp_processor_id() in order to avoid the noise, and also adds a WARN_ON_ONCE() to the call to set_cpus_allowed_ptr() in order to directly detect immediate failure. There is no WARN_ON_ONCE() within the test loop, allowing human-reflex-based affinity resetting, if desired. Signed-off-by: Paul E. McKenney

refscale: Add acqrel, lock, and lock-irq

2021-05-10T23:05:05Z

This commit adds scale_type of acqrel, lock, and lock-irq to test acquisition and release. Note that the refscale.nreaders=1 module parameter is required if you wish to test uncontended locking. In contrast, acqrel uses a per-CPU variable, so should be just fine with large values of the refscale.nreaders=1 module parameter. Signed-off-by: Paul E. McKenney

torture: Make refscale throttle high-rate printk()s

2021-01-07T01:17:20Z

This commit adds a short delay for verbose_batched-throttled printk()s to further decrease console flooding. Signed-off-by: Paul E. McKenney

refscale: Allow summarization of verbose output

2021-01-07T01:08:09Z

The refscale test prints enough per-kthread console output to provoke RCU CPU stall warnings on large systems. This commit therefore allows this output to be summarized. For example, the refscale.verbose_batched=32 boot parameter would causes only every 32nd line of output to be logged. Signed-off-by: Paul E. McKenney

refscale: Prevent hangs for invalid arguments

2020-11-07T01:13:51Z

If an refscale torture-test run is given a bad kvm.sh argument, the test will complain to the console, which is good. What is bad is that from the user's perspective, it will just hang for the time specified by the --duration argument. This commit therefore forces an immediate kernel shutdown if a ref_scale_init()-time error occurs, thus avoiding the appearance of a hang. It also forces a console splat in this case to clearly indicate the presence of an error. Signed-off-by: Paul E. McKenney

refscale: Bounds-check module parameters

2020-11-03T01:13:29Z

The default value for refscale.nreaders is -1, which results in the code setting the value to three-quarters of the number of CPUs. On single-CPU systems, this results in three-quarters of the value one, which the C language's integer arithmetic rounds to zero. This in turn results in a divide-by-zero error. This commit therefore adds bounds checking to the refscale module parameters, so that if they are less than one, they are set to the value one. Reported-by: kernel test robot Tested-by "Chen, Rong A" Signed-off-by: Paul E. McKenney

refperf: Avoid null pointer dereference when buf fails to allocate

2020-08-25T01:45:35Z

Currently in the unlikely event that buf fails to be allocated it is dereferenced a few times. Use the errexit flag to determine if buf should be written to to avoid the null pointer dereferences. Addresses-Coverity: ("Dereference after null check") Fixes: f518f154ecef ("refperf: Dynamically allocate experiment-summary output buffer") Signed-off-by: Colin Ian King Signed-off-by: Paul E. McKenney